signals-scout-data-pipelines
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a standard diagnostic tool with no malicious code or unauthorized access patterns detected. All operations are conducted via project-specific MCP tools.- [PROMPT_INJECTION]: The skill defines a clear operational role and logic without attempting to override system safety guidelines or extract system prompts.- [DATA_EXFILTRATION]: No unauthorized data transmission or access to sensitive local files (e.g., .ssh, .aws) was identified. Data reporting uses the platform's provided 'emit' tool.- [REMOTE_CODE_EXECUTION]: The skill does not perform remote script downloads or dynamic code execution (eval/exec). Dependencies are not used.- [PROMPT_INJECTION]: Regarding Indirect Prompt Injection (Category 8):\n
- Ingestion points: Reads logs and error messages from
cdp-functions-logs-retrieve,workflows-logs, andbatch-export-getin SKILL.md.\n - Boundary markers: Explicitly instructs the agent to treat this data as 'untrusted snippets' and ignore embedded instructions.\n
- Capability inventory: Uses
signals-scout-emit-signalto report findings andsignals-scout-scratchpad-rememberfor state persistence.\n - Sanitization: Instructs the agent to truncate long messages and drop payload echoes to prevent processing untrusted content as instructions.
Audit Metadata